Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ruslan-korneev/claude-plugins/clean-reviewgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ruslan-korneev/claude-plugins/clean-review)<a href="https://agentmods.dev/commands/ruslan-korneev/claude-plugins/clean-review"><img src="https://agentmods.dev/badge/commands/ruslan-korneev/claude-plugins/clean-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00759 |
| Opus 5 | $0.00008 | $0.00380 |
| Sonnet 5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
clean:review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /clean:review
Analyze code for code smells and clean code principle violations.
Instructions
Step 1: Read the code
Read the specified file or files in the directory.
Step 2: Check for code smells
Look for the following problems:
Bloaters
- Long Method — functions > 20-30 lines
- Long Parameter List — > 3-4 parameters
- Large Class — classes > 200 lines with unrelated methods
- Primitive Obsession — primitives instead of Value Objects
Object-Orientation Abusers
- Switch Statements — long if/elif by type
- Refused Bequest — subclass doesn't use parent's methods
Change Preventers
- Divergent Change — class changes for different reasons
- Shotgun Surgery — one change affects many classes
Dispensables
- Dead Code — unused code
- Speculative Generality — code "for the future"
- Comments — comments instead of clear code
Couplers
- Feature Envy — method envies another class's data
- Inappropriate Intimacy — classes are too coupled
- Message Chains — long call chains
Step 3: Check principles
SOLID
- SRP — class has one reason to change?
- OCP — extension without modification?
- LSP — subclasses replace parents?
- ISP — interfaces not "fat"?
- DIP — dependency on abstractions?
Other
- DRY — no knowledge duplication?
- KISS — no unnecessary complexity?
- YAGNI — no code "for the future"?
Step 4: Check naming
- Variables — nouns, reveal meaning
- Booleans — is_/has_/can_/should_
- Functions — verb + noun
- Classes — nouns, specific names
- Constants — SCREAMING_SNAKE_CASE
Response Format
## Code Review: {{ path }}
### Summary
- **Overall assessment**: Good / Needs attention / Critical
- **Issues found**: X
### Code Smells
#### Critical
- **Long Method** (lines X-Y): `function_name` — 80 lines
- Recommendation: Extract Method
#### Warning
- **Primitive Obsession** (line X): `email: str` instead of `Email` Value Object
### Principle Violations
#### SRP
- `UserService` — 3 reasons to change: DB work, validation, notifications
### Naming Issues
- Line X: `d = 86400` → `SECONDS_IN_DAY = 86400`
- Line Y: `def process()` → `def calculate_order_total()`
### Recommendations
1. **Priority 1**: Split `process_order()` into separate functions
2. **Priority 2**: Extract `EmailService` from `UserService`
3. **Priority 3**: Create Value Object for Email
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 108 lines · 16 tokens per session scan A 9816f6a05273
clean:review is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 759 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
guide
Ask the plugin about itself — what a config key does, how the plan gate grades, what the journal can prove — answered from its own docs with a citation for every claim, by the read-only guide agent.
init
在既有專案初始化 Octopus——摸專案、檢查 OpenSpec CLI 與結構(缺則引導安裝)、盤點 change 狀態、建 Arena、出交接報告。每個專案跑一次。.
spec
SDD 前半段:需求釐清(反問+挑戰)→ OpenSpec change 一次落檔(proposal+delta+tasks,Draft)→ TPM 拍板鎖定(回一個 OK 即可)。鎖定後 build 全自主執行。.
debug
用 Agent 工具啟動 debugger agent,把錯誤資訊原文(含截圖/log)完整轉給它。.
db
DB 三方言諮詢(SQL Server / SQLite / PostgreSQL)—— DBA 直答(唯讀,不連 DB).
overview
專案鳥瞰——Scout 出敘事型 overview(分層架構+模組職責+依賴方向+關鍵流程走讀)。唯讀、不落檔,每次都是現況。.